© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83275
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     R
    0.80
     الر
    0.57
    Amber
    0.55
     आर
    0.54
     Amber
    0.52
     amber
    0.50
    R
    0.49
     Rou
    0.48
     Р
    0.45
     Lauderdale
    0.43
    POSITIVE LOGITS
    மலை
    0.41
     בני
    0.37
    ണ്ടും
    0.36
     Bina
    0.36
    ેલી
    0.36
    Це
    0.36
    䚲
    0.36
    സില്‍
    0.35
     Wellington
    0.35
     patri
    0.34
    Activations Density 0.004%

    No Known Activations